Search

Sentiment analysis furnishes consumer concerns regarding products, enabling product enhancement development. Existing sentiment analysis using machine learning techniques is computationally intensive and less reliable. Deep learning in sentiment analysis approaches such as long short term memory has adequately evolved, and the selection of optimal hyperparameters is a significant issue. This study combines the LSTM with differential grey wolf optimization (LSTM-DGWO) deep learning model. The app review dataset is processed using the bidirectional encoder representations from transformers (BERT) framework for efficient word embeddings. Then, review features are extracted by the genetic algorithm (GA), and the optimal review feature set is extracted using the firefly algorithm (FA). Finally, the LSTM-DGWO model categorizes app reviews, and the DGWO algorithm optimizes the hyperparameters of the LSTM model. The proposed model outperformed conventional methods with a greater accuracy of 98.89%. The findings demonstrate that sentiment analysis can be practically applied to understand the customer’s perception of enhancing products from a business perspective.

Compressed sensing (CS) or compressive sampling has shown an enormous potential to reconstruct a signal from its highly under‐sampled observations. A high dimensional image processing system can adopt the CS paradigm to reduce the storage and the transmission burden. However, a large sensing system (matrix) is required to capture high dimensional images. The CS reconstruction algorithms demand heavy computational requirement due to the use of large sensing matrix. It sometimes becomes impractical to implement a sensing system of the desired size due to the limited access to the CPU memory. To address this issue, the present work proposes a deep learning based CS framework that uses a convolutional neural network to enable capturing of a high dimensional image by utilizing a multi‐layer subsampling and filtering operations. The proposed approach uses another convolutional neural network that reconstructs the original image without depending on the sensing network at a significantly reduced computational cost. Extensive simulation results show that the proposed method reconstructs a high dimensional image with an improved PSNR value by 1.5±0.63 dB, SSIM value by 0.04±0.02 and FSIM value by 0.02±0.02 compared to the other state‐of‐the‐art methods in less than 1.4 seconds.

Motion estimation (ME) plays an important part in the functioning of the video codec by identifying and reducing the temporal redundancies in between successive frames of a video sequence. Block matching algorithm (BMA) has been accepted as one of the finest approaches for motion estimation due to its efficiency and ease of implementation. This paper presents a new and improved iterative and adaptive search strategy for block-based motion estimation along with its efficient hardware implementation. Since it is expected that there will be more demand for streaming video services on mobile devices, designing fine tuning algorithm with dedicated efficient hardware would provide significant benefits. The present motion estimation algorithm is adaptive in nature that takes into consideration the motion content of the current frame while predicting the motion vector. The adaptive nature of the search eases the complexity of motion estimation and the algorithm makes use of the correlation present among the motion vectors of the neighboring blocks to lower the number of search position. Traditionally, such adaptive algorithms are executed by CPU cores running a software stack. Since software involves a significant amount of overheads like fetching into cache, branches, stalls etc., the efficiency of the proposed algorithm can be overshadowed by the hardware platform. To avoid this, compact hardware architecture was developed which stands ahead of other existing architectures as shown in comparison. The VLSI design for the proposed algorithm presented in this work deals with the generation of the adaptive search pattern and use of interleaved memory organization fasten the operational speed. A profitable data re-use scheme and involvement of minimum processing elements required for parallelization reduce the on-chip area. Working at a frequency of 243 MHz, the proposed design can process 66 720p HD (1280 × 720) frames in one second consuming an area of 38.2 K gate equivalent. Hence, the proposed design can be incorporated in video codecs to be used in commercial devices like camcorders, smart phones and other portable, battery-powered video consumer devices. The proposed research method achieves significantly improved results both in terms of algorithmic metrics (PSNR) as well hardware performance (speed, area).

The paper presents an efficient VLSI architecture for fast Motion Estimation in video codec using modified Adaptive Rood Pattern Search Algorithm. The proposed architecture uses an interleaved memory arrangement and an early check technique to compute the Sum of Absolute Differences. The proposed design can process High Definition (1080p) video frames in real time while optimizing the hardware area. The architecture has been implemented in verilog HDL and mapped to 45 nm FPGA. It uses only 6.8K gates for the implementation of the datapath and the controller. It achieves a maximum frequency of 120 MHz. However, working at 100 MHz, it is able to process 60 HD ( $$1920\times 1080$$ ) frames per second while consuming 39 mW of power. The proposed architecture achieves premium speed with an optimum power and area requirements and can be suitably incorporated in light-weight video-intensive devices like smart-phones, tablet computers.

Background The Electroencephalogram (EEG) signal is a time series depictive signal that contains the useful knowledge about the state of the brain. It has high temporal resolution for detection of chronic brain disorders such as epilepsy/seizure, dementia, sleep apnea, schizophrenia, etc. In this work, EEG is a prime concern for seizure/epilepsy detection and localization. Methods Entropy estimator is a good solution to this problem. Here, the time series complexity analysis of brain signal is carried using five different entropy estimators: Shannon Entropy, Renyi Entropy, Approximate Entropy, Sample Entropy, and Fuzzy Entropy. The average entropy values of EEG signal is significantly found lower for epileptic data sets compared to non-epileptic EEG. Results Experimental results evaluated for discriminating ability of each entropy measure demonstrated that among all entropies, Fuzzy Entropy discriminates between epileptic EEG and non-epileptic EEG more efficiently with a minimum p-value (0.001) compared to other four entropy estimators. Fuzzy Entropy defines the similarity between two vectors fuzzily on the basis of exponential function. Unlike to Approximate and Sample Entropy, the Fuzzy Entropy is free from parameter limitations and offers efficient results even for the small tolerance (r Conclusion The Fuzzy entropy gives better stability and consistency with highest discriminating ability compared to other entropy estimators. Eventually, results for detection and localization of epilepsy for affected channel and region through the variance and FuzzyEn are cross-validated by expert Neuro-physician.

AimsDiagnostic ambiguities regarding the malignant potentiality of oral submucous fibrosis (OSF), an oral precancerous condition having dysplastic and non-dysplastic isoforms are the major failure for early intervention of oral squamous cell carcinoma (OSCC) patients. Our goal is to identify proteomic signatures from biopsies that can be used as precancer diagnostic marker for patient suffering from OSF.MethodsThe high throughput techniques adopting de novo peptide sequencing (1D SDS-PAGE coupled nanoLC MALDI tandem mass spectrometry (MS/MS)-based peptide mass fingerprint), immunohistochemistry (IHC), Western blot (WB) and real-time PCR (RT-PCR) analysis are considered for such biomarker identification and multilevel validations.ResultsAlpha-enolase is identified as an overexpressed protein in biopsies of oral submucous fibrosis with dysplasia (OSFWD) compared with oral submucous fibrosis without dysplasia (OSFWT) and normal oral mucosa (NOM). Total proteome analysis of an overexpressed protein band around 47 kDa of OSFWD identifies 334 peptides corresponding to 61 human proteins. Among them α-enolase is identified as a prime protein with highest number of peptides (44 out of 334 peptides) and sequence coverage (66.4%). Furthermore, RT-PCR, WB and IHC analysis also show mRNA and tissue level upregulation of α-enolase in OSFWD validating α-enolase as precancer marker.ConclusionsThis study for the first time identifies and validates α-enolase as a novel biomarker for early diagnosis of malignant potentiality of OSF. Hence, the identified protein marker, α-enolase can help in early therapeutic intervention of OSF patients leading to the reduction of patient’s pain, treatment cost and enhancement of patient’s quality of life.

Compressed Sensing (CS) or Compressive Sampling is an integral component in the reconstruction of image from sub-sample (incomplete) measurements. In many practical situations, multiple channel sensing, followed by suitable fusion strategy, reconstruct images with high spatial and spectral information. This paper proposes an efficient combining scheme on CS measurements to reconstruct an image from highly incomplete multi-channel degraded and noisy observations (measurements). A linear regression scheme has been used here to estimate the weights for different channels/sensors. The estimated weights are then used to form a set of composite measurements through a weighted averaging technique. The optimal weighted measurements are then used in an l1-minimization framework to reconstruct the image. A set of extensive simulation results show appreciable reduction in artifacts and visual improvement with enhanced contrast. Simulation results also demonstrate that the proposed method outperforms some popular image fusion methods in both subjective and objective qualities for image reconstruction, irrespective of the degree of degradation in multi-channel input CS measurements. HighlightsMulti-channel image fusion from degraded compressed sensing measurements.Degradation includes both multiplicative (random scaling) and additive noise.Linear regression for set of optimal weight calculation and rONE-L1 reconstruction.Improvement in PSNR by 20.34dB over the existing methods at 70% measurements.

The longer scanning time requirement in Magnetic Resonance Imaging (MRI) can one way be overcome through parallel data acquisition technique. The scanning time in pMRI systems can further be reduced through calibrationless data acquisition process that eliminates the need of extra k-space data. Compressed Sensing (CS) or Compressive Sampling in data acquisition again reduces this scanning time as image reconstruction is done from the undersampled k-space measurements. To this aim, the present work proposes a calibrationless CS regularized pMRI approach. A Stacked Convolutional Denoising Autoencoder (SCDAE) is used for accurate estimation of the coil-wise sensitivity maps. The present work also uses an interferometry modulated Radio Frequency (RF) coil that not only enhances the resolution in the Field of View (FoV), but also reduces the interference on the adjacent FoVs. Extensive simulation results show that the proposed method enables reconstruction of an MR image with size 256 × 256 from 25% measurements in approximately 0.57 s and offers a performance improvement in Peak-Signal-to-Noise Ratio (PSNR) by 2 ± 0.18 dB and Structural SIMilarity (SSIM) by 0.2 ± 0.06 over the state-of-the-art methods.

Block-based motion estimation plays a significant role in video codecs by exploiting and reducing the temporal redundancies that exist between consecutive frames in a video sequence. Adaptive Rood Pattern Search (ARPS) is one of the most popular fast motion estimation algorithms. In this paper, VLSI design for the ARPS algorithm is proposed that involves reasonably limited hardware resource without compromising the real-time speed for transmitting HD videos. To tackle the adaptive nature of the algorithm, the proposed design avoids systolic arrays and introduces novel pattern generation methodology that can tackle the adaptive nature of the algorithm. Further, the design incorporates interleaved memory organization with a well-defined sharing strategy to re-use data and ensures high throughput. Working at a frequency of 112MHz, the present design can process 30 Full HD 1080p (1920×1080) frames using only 47.15K gates. Hence, the proposed VLSI architecture can be incorporated in video codecs that can be suitably used in devices like camcorders, tablets and smart phones.

Electroencephalogram (EEG) signal has numerous applications in the field of medical science. It is used to diagnose many of the abnormalities, disorders, and diseases related to the human brain. The EEG signal contaminated with ocular artifacts makes it very difficult for analysis and diagnosis. This paper includes work on classification of artifactual/non-artifactual EEG time series and perfect detection of eye movement (EM) artifact contaminated EEG signal along with multiple EM artifactual zones in the same time series. Artificial Neural Network classifier in a simple perceptron model without hidden layer is used for the identification. This study presents a newly developed, simple, robust, and computationally fast statistical Time-Amplitude algorithm. By the application of novel Time-Amplitude algorithm on identified signal, the EM artifactual EEG signal along with multiple zones is automatically detected and marked accurately. Such robust, efficient, real-time and simple algorithm is not ever designed and used for ocular artifact detection by any author. The ROC analysis gives accuracy of the ANN model for classifying the presence of artifacts in the EEG data, which is 97.50 %. The time elapsed for executing the Time-Amplitude algorithm for automatic detection of EM artifact is very less (4.30 msec.) compared to DWT with Haar. It has the capability to detect multiple EM artifactual zones, in the same time, for the montage of 8-second EEG.

Motion estimation accounts for major part of the computational complexity of any video coding standard. In this paper, we present efficient VLSI architecture for the implementation of hexagonal search algorithm for fast motion estimation. The proposed architecture employs sequential processing of pixel data rather than parallel processing in order to reduce the hardware area substantially while achieving the real-time speed. A novel on-chip memory organization is proposed, which reduces the address generation complexity and helps improve the speed. The architecture when implemented in Verilog HDL and mapped to Virtex-5 FPGA achieves a maximum frequency of 340 MHz, while the gate count is calculated to be 3.1 K. Thus, the proposed architecture is considered suitable to be incorporated in commercial devices such as camcorders and smart phones.

Cancer cells use aberrant metabolic process for proliferation and metastasis. High-throughput separation and quantification of metabolites from bio-samples is crucial in this aspect. Matrix Assisted Laser Desorption Ionization Mass Spectrometry (MALDI MS), a prime technique used for metabolite identifications, suffers from several limitations in quantification studies. In this study, we have established a novel approach using conventional nanoLC-MALDI MS/MS interface for separation, identification and label free quantifications of the metabolites from biopsies. Quantification of metabolite using MALDI requires a homogeneous distribution of the matrix mixed samples on target plate for proportional time-of-flight (ToF) with the concentration of a particular metabolite present in that sample under same laser intensity. Here, crude metabolites extracted from cancer biopsies are separated and eluted as ‘fraction spots’ on MALDI target plate using nanoLC. Introducing a novel parameter, %aAUC (percentage of average area under the curve), comparative quantification of separated metabolites isolated from normal, pre-cancer and cancer biopsies has been explored. Such comparative quantification is only possible with multiple AUCs of a particular metabolite obtained from this nanoLC-MALDI MS approach. Further, selected metabolite peaks have been analyzed through MS/MS fragmentation. This approach was validated using known concentrations of an internal standard (thiourea) with its corresponding aAUC (average area under the curve). Interestingly, such comparative quantification has revealed a significant change in expression of crucial lipid metabotypes like triglyceride, phospatidyl inositol, phosphatidyl choline, glycerophospholipid, cytidine diphosphate-diacylglycerol and phosphatidylinositol bisphosphate indicating altered lipid metabolism associated membrane biogenesis in oral pre-cancer (oral submucous fibrosis) and cancer. Hence, our study successfully established an altered membrane biogenesis in oral cancer using a novel and distinct approach for separation, identification and label-free quantification of metabolites in fast growing metabotype-biomarker identification era.

Motion estimation (ME) is crucial to the performance of a video codec as it recognizes and mitigates temporal redundancies between consecutive frames of a video sequence. It is one of the most computationally intensive blocks in the video encoder. Block matching algorithm (BMA) is considered as one of the best approaches for performing ME due to its ease of implementation and efficiency. Several ME algorithms are based on fixed search patterns while the others are adaptive in nature and exploit the correlation present between neighboring macroblocks of a video frame. This paper introduces an efficient ME algorithm named Hexagon Based Compressed Diamond Algorithm (HCDA) that tries to reduce the complexity of ME by lowering the number of search points in the process. The algorithm uses an early termination technique and an adaptive search pattern that can uniformly deal with slow and fast motion content in a video. The proposed HCDA uses dual threshold technique based on the available spatial information. This further helps in terms of clock cycles or hardware resources during VLSI implementation. Moreover, VLSI design for HCDA can explore the adaptive nature of the algorithm and the adopted search methodology is handled by interleaved memory organization that enhances the operational speed. Supportive data re-use scheme with effective block for SAD computation contributes to a fair trade-off between speed and on-chip area. The designs can work at a maximum frequency of 262 MHz to process 76 HD (1280 × 720) frames per second. The corresponding gate count comes out to be 35.8 K gate equivalent. The encouraging experimental results obtained under various defined metrics indicate suitability of the proposed hardware architecture for its inclusions in portable battery powered consumer video devices.